K

Kokorotts

Developed by Daemontatox
Kokoro is an open-source text-to-speech model with 82 million parameters, delivering sound quality comparable to large models through a lightweight architecture while significantly improving speed and cost efficiency.
Downloads 78
Release Time : 2/27/2025

Model Overview

Kokoro is a multilingual text-to-speech model based on the StyleTTS2 architecture, supporting 8 languages and 54 voice styles, suitable for various deployment scenarios from production environments to personal projects.

Model Features

Lightweight and Efficient
A lightweight architecture with only 82 million parameters yet delivers sound quality comparable to large models
Multilingual Support
Supports 8 languages and 54 voice styles to meet diverse needs
Open-Source License
Licensed under Apache-2.0, freely deployable for commercial and personal projects
Low-Cost Training
Requires only $1,000 in training costs (1000 A100 GPU hours)

Model Capabilities

High-quality text-to-speech
Multilingual speech synthesis
Voice style switching
Speech rate adjustment

Use Cases

Content Creation
Audiobook Generation
Convert text content into natural speech
Supports multiple languages and voice style options
Assistive Technology
Voice-Assisted Applications
Provide speech output functionality for visually impaired users
Lightweight model suitable for mobile deployment
Education
Language Learning Tools
Generate multilingual pronunciation examples
Supports accurate pronunciation in 8 languages
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase